The proposal accounts for 4% of the grade. Proposal page limit: 2 pages.
IMPORTANT: One proposal per group; submit your group's name/members using this form by March 11 (4 days before the proposal submission date) so we can create the entry in bcourses.
You must include answers to the following questions. Please use them as sections in your document.
State the hypothesis of your project. What is the question that you are seeking to explore, understand, and to some extent answer? What might be the results of this investigation?
Context. Will you be working with others on this? Is it a subproject in the context of a larger research effort? Are variants of it going to be utilized in other classes?
Key prior work. What are a few (~3) pieces of prior work that this builds upon, is motivated by, to be contrasted with?
Empirical methodology. What will be done to investigate this question and establish the results? What resources will be needed for that?
Challenges and Obstacles. What do you anticipate might present a problem that will prevent you from pursuing this investigation as fully as you would like?
You are required to present your project on one of two poster session days: April 23 or April 25. Times, details, and format TBD.
Project final report length limit: 10 pages, single-column standard latex. Due Tuesday, May 7 11:59 PST. This is a strict deadline as we need to finish grading by the final grades due date. The final project and poster presentation account for 40% of the the grade. The pre-proposal accounts for 1% of grade and proposal for 4%.
Group size: max 3 people. You may choose to work in a group distinct from the groups you used for homework 1, 2, and 3.
You are encouraged to discuss your preliminary project ideas with instructors. Just request an appointment.
You are welcome and encouraged to have your own project ideas. This is especially true if you want to bring parallelism to your ongoing research projects. In addition, we (as the CS267 team) have a few potential ideas below, which you can access at the following Google document. You must be logged in with your Berkeley email account to view it.
Project Ideas from the Course Staff (this document will be updated regularly as more ideas come in)
Below are components that will make up your project grade and the first two components are the most important:
Practical content/creativity; implementation/tuning effort.
Experimental data: scaling/performance analysis/interesting inputs or outputs.
Theoretic content/creativity; design/analysis of algorithms.
Impact: difficulty and timeliness of the contribution.
We understand that not all projects will have all four components but it is expected that the first two components will be present in all projects. As such, we expect the majority of your final report to be about parallelism, and not the problem description.
We want you to do hands-on parallel programming in your projects. Therefore, frameworks that automatically parallelize computations, such as those developed for deep learning programs, are only admissible as a comparison point to your own implementations.
Similarly, autotuning and code generation software is only admissible as comparison points to your implementations. One exception to this rule is when your project has a large scope with a limited use of autotuning or code generation (for example a large distributed computational chemistry software that needs fast single node matrix multiplication code). In such cases, the use of autotuners or code generators can be permitted in a case-by-case basis as long as the rest of the project has hands-on parallel programming.
Posters and abstracts from CS267 in Spring 2022
Berkeley students: please submit a PDF file (only a PDF will be accepted) to bCourses.